Small-size pedestrian detection in large scene based on fast R-CNN

Shengke Wang; Na Yang; Lianghua Duan; Lu Liu; Junyu Dong

doi:10.1117/12.2305889

10 April 2018 Small-size pedestrian detection in large scene based on fast R-CNN

Shengke Wang, Na Yang, Lianghua Duan, Lu Liu, Junyu Dong

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106150J (2018) https://doi.org/10.1117/12.2305889
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

Pedestrian detection is a canonical sub-problem of object detection with high demand during recent years. Although recent deep learning object detectors such as Fast/Faster R-CNN have shown excellent performance for general object detection, they have limited success for small size pedestrian detection in large-view scene. We study that the insufficient resolution of feature maps lead to the unsatisfactory accuracy when handling small instances. In this paper, we investigate issues involving Fast R-CNN for pedestrian detection. Driven by the observations, we propose a very simple but effective baseline for pedestrian detection based on Fast R-CNN, employing the DPM detector to generate proposals for accuracy, and training a fast R-CNN style network to jointly optimize small size pedestrian detection with skip connection concatenating feature from different layers to solving coarseness of feature maps. And the accuracy is improved in our research for small size pedestrian detection in the real large scene.

Citation Download Citation

Shengke Wang, Na Yang, Lianghua Duan, Lu Liu, and Junyu Dong "Small-size pedestrian detection in large scene based on fast R-CNN", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106150J (10 April 2018); https://doi.org/10.1117/12.2305889

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available